CN111736581A

CN111736581A - Global path planning method and device for intelligent mobile equipment

Info

Publication number: CN111736581A
Application number: CN201910209400.6A
Authority: CN
Inventors: 栾成志
Original assignee: Beijing Qihoo Technology Co Ltd
Current assignee: Beijing Qihoo Technology Co Ltd
Priority date: 2019-03-19
Filing date: 2019-03-19
Publication date: 2020-10-02
Anticipated expiration: 2039-03-19
Also published as: CN111736581B

Abstract

The invention discloses a global path planning method and a global path planning device for intelligent mobile equipment. The global path planning method of the intelligent mobile equipment determines the tracking object, determines the target point according to the current position of the tracking object and plans the path from the current position of the intelligent mobile equipment to the target point. And tracking the tracked object, and adjusting the target point according to the tracking result. And re-planning the path according to the adjusted target point. According to the technical scheme, before tracking is started, the advancing direction of the intelligent mobile equipment is determined, so that the intelligent mobile equipment has advancing basis, and loss caused by too high moving speed of a tracked object is avoided. In the tracking process, prejudgment is carried out in advance, the position of the target point is adjusted in time, the advancing direction of the intelligent mobile equipment is adjusted, invalid advancing is avoided, and tracking efficiency is improved.

Description

Global path planning method and device for intelligent mobile equipment

Technical Field

The invention relates to the technical field of intelligent mobile equipment, in particular to a global path planning method and a global path planning device of intelligent mobile equipment.

Background

In the prior art, an intelligent mobile device, such as a sweeping robot, generally travels according to a planned path. Therefore, under the condition that the sweeping robot does not know the layout of the room, the sweeping robot cannot plan a correct traveling route, and the sweeping is not thorough. Meanwhile, the sweeping robot has the danger of collision with obstacles, and the sweeping robot can be damaged. And when the back that bumps, the robot of sweeping the floor needs get rid of poverty to avoid the barrier, will accelerate the electric quantity consumption like this, influence moreover and clean the work, lead to work efficiency to reduce. Therefore, a corresponding solution is needed.

Disclosure of Invention

In view of the above, the present invention has been made to provide a global path planning method, apparatus, electronic device and computer-readable storage medium for a smart mobile device that overcome or at least partially solve the above-mentioned problems.

According to an aspect of the present invention, a global path planning method for an intelligent mobile device is provided, including:

determining a tracking object;

determining a target point according to the current position of the tracking object, and planning a path from the current position of the intelligent mobile equipment to the target point;

tracking the tracked object, and adjusting the target point according to a tracking result;

and re-planning the path according to the adjusted target point.

Optionally, the determining the tracking object comprises:

and detecting through a depth camera and/or a laser radar, and determining the detected object which accords with the preset characteristics as a tracking object.

Optionally, the planning a path from the current location of the smart mobile device to the target point comprises:

and searching a track line from the current position of the intelligent mobile device to the target point based on the A-x algorithm.

Optionally, the tracking object includes:

detecting at a preset frequency;

and taking the detected object which accords with the preset characteristics as a tracking object, and recording the position of the detected tracking object.

Optionally, the adjusting the target point according to the tracking result includes:

determining a predicted position according to the positions of the tracking objects recorded for the last times;

if the object which accords with the preset characteristics is continuously detected in a second preset range of the predicted position, taking the object which accords with the preset characteristics detected this time as a tracking object;

and taking the position of the detected tracking object as an adjusted target point.

Optionally, the determining a predicted position according to the last recorded positions of the tracking object includes:

and performing Kalman filtering processing on the positions of the tracking objects recorded for a plurality of times recently.

Optionally, the taking the object which is detected to meet the preset characteristic as the tracking object includes:

and if a plurality of objects which accord with the preset characteristics are detected, taking the object which is closest to the predicted position as a tracking object.

Optionally, the method further comprises:

if the current position of the intelligent mobile device and the range of the adjusted target point are within a first preset range, the path is not re-planned according to the adjusted target point.

Optionally, the replanning the path according to the adjusted target point includes:

and if the position change speed of the tracked object is determined to be greater than the preset speed according to the tracking result, determining a starting point according to a first preset range with the current position of the intelligent mobile equipment as the circle center and the currently planned path, and planning the path from the starting point to the adjusted target point.

Optionally, the smart mobile device is a sweeping robot, and the tracking object is a human body.

According to another aspect of the present invention, there is provided a global path planning apparatus for an intelligent mobile device, including:

a determination unit adapted to determine a tracked object; determining a target point according to the current position of the tracking object, and planning a path from the current position of the intelligent mobile equipment to the target point;

the adjusting unit is suitable for tracking the tracking object and adjusting the target point according to a tracking result;

and the path planning unit is suitable for re-planning the path according to the adjusted target point.

Optionally, the determining unit is adapted to perform detection by a depth camera and/or a laser radar, and determine the detected object meeting the preset characteristics as the tracking object.

Optionally, the determination unit is adapted to search for a trajectory from the current location of the smart mobile device to the target point based on an a-algorithm.

Optionally, the adjusting unit is adapted to perform detection at a preset frequency;

Optionally, the adjusting unit is further adapted to determine a predicted position according to the last recorded positions of the tracked object;

Optionally, the adjusting unit is further adapted to perform kalman filtering processing on the positions of the tracking object recorded several times last.

Optionally, the adjusting unit is further adapted to, if a plurality of objects that meet the preset characteristic are detected, take an object that is closest to the predicted position as a tracking object.

Optionally, the apparatus further comprises:

and the judging unit is suitable for not replanning the path according to the adjusted target point if the current position of the intelligent mobile equipment and the range of the adjusted target point are within a first preset range.

Optionally, the path planning unit is adapted to determine a starting point according to a first preset range in which the current position of the intelligent mobile device is a circle center and a currently planned path if it is determined that the position change speed of the tracked object is greater than a preset speed according to the tracking result, and plan a path from the starting point to the adjusted target point.

In accordance with still another aspect of the present invention, there is provided an electronic apparatus including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform a method as any one of the above.

According to a further aspect of the invention, there is provided a computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement a method as any one of the above.

According to the technical scheme, the target point is determined according to the current position of the tracking object by determining the tracking object, and the path from the current position of the intelligent mobile equipment to the target point is planned. And tracking the tracked object, and adjusting the target point according to the tracking result. And re-planning the path according to the adjusted target point. According to the technical scheme, before tracking is started, the advancing direction of the intelligent mobile equipment is determined, so that the intelligent mobile equipment has advancing basis, and loss caused by too high moving speed of a tracked object is avoided. In the tracking process, prejudgment is carried out in advance, the position of the target point is adjusted in time, the advancing direction of the intelligent mobile equipment is adjusted, invalid advancing is avoided, and tracking efficiency is improved.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 shows a flow diagram of a global path planning method of an intelligent mobile device according to an embodiment of the invention;

fig. 2 is a schematic structural diagram of a global path planning apparatus of an intelligent mobile device according to an embodiment of the present invention;

FIG. 3 shows a schematic structural diagram of an electronic device according to one embodiment of the invention;

fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Fig. 1 is a flowchart illustrating a global path planning method for an intelligent mobile device according to an embodiment of the present invention. As shown in fig. 1, the method includes:

and step S110, determining the tracking object, determining a target point according to the current position of the tracking object, and planning a path from the current position of the intelligent mobile equipment to the target point.

The intelligent mobile device can be any intelligent device capable of moving, such as a sweeping robot, an unmanned mobile platform and the like. The tracking object has the movable capability and is an object, such as a person, which the intelligent mobile device needs to follow. The intelligent mobile device needs to prejudge the target point of the tracked object in advance and plan a path to the target point, so as to achieve a better tracking effect. For example, if the tracking object is at the front right of the smart mobile device, the target point is determined to be at the front right and farther than the tracking object, so as to plan the path. Therefore, before tracking is started, the advancing direction of the intelligent mobile equipment is determined, so that the intelligent mobile equipment has advancing basis, and loss caused by too high moving speed of a tracked object is avoided.

And step S120, tracking the tracking object, and adjusting the target point according to the tracking result.

The tracking object has autonomous mobility, so the position of the target point needs to be continuously adjusted in the tracking process. In the above example, if the movement locus of the tracking target deviates to the left, the target point is adjusted from the right front to the left front in time, and the advance judgment is performed.

Step S130, replanning the path according to the adjusted target point.

The position of the target point is adjusted, the advancing path is correspondingly re-planned, the advancing direction of the intelligent mobile equipment is adjusted, invalid advancing is avoided in time, and the tracking efficiency is improved.

In one embodiment of the present invention, as in the method shown in fig. 1, the determining the tracked object in step S110 includes: and detecting through a depth camera and/or a laser radar, and determining the detected object which accords with the preset characteristics as a tracking object.

The depth camera or the laser radar can be used for scanning and detecting, and can be arranged on the intelligent mobile equipment to obtain a detection result of the surrounding environment of the intelligent mobile equipment.

In one specific example, the human leg is detected with a single line laser. Specifically, the surrounding environment of the intelligent mobile device is scanned through single-line laser to obtain a plurality of scanning points. According to the distribution condition of a plurality of scanning points, one or more sections of curves which are formed by the scanning points and conform to the characteristics of circular arcs are identified. And judging whether the identified curves conform to the characteristics of the human legs, and if so, determining the detected human body position according to the corresponding curves.

The single-line laser is arranged on the intelligent mobile device and scans by emitting laser to obtain a scanning point. The obtained scanning points can reflect the outline information of the object and the position information of the object. The single-line laser has high working efficiency, and if the single-line laser is rotated, scanning points of the object profile within 360-degree range of the intelligent mobile device can be obtained, so that the scanning range is expanded. The intelligent mobile device of the embodiment needs to detect people in the surrounding environment, so that the human body information existing in the surrounding environment is acquired through single-line laser scanning.

And processing the scanning points, analyzing and obtaining specific information of the surrounding environment, for example, sequentially connecting the scanning points to obtain the outline of the object, and judging the attribute of the object according to the outline so as to judge whether people exist in the surrounding environment. Human body outline is mostly the curve, lacks sharp-pointed edges and corners, through the curve that whether discernment exists the coincidence ring characteristic that one section or multistage scanning point constitutes, just can effectually discern whether human body in the surrounding environment. And identifying whether the curve conforms to the arc characteristics or not, wherein the curve can be changed through the curvature of the curve, and if the curvature is changed and is changed greatly, the curve conforms to the arc characteristics.

Of course, there may be other objects in the surrounding environment that are contoured to follow the curve of the circular arc feature, such as a cylindrical table or chair. Therefore, it is necessary to further determine whether the curve corresponding to the circular arc feature corresponds to the human leg feature, for example, whether the width, curvature, etc. of the curve correspond to the human leg contour. Only when the curve conforms to the characteristics of the human leg, the curve is judged to belong to the contour of the human leg, and the position of the curve is the position of the human body. After the position of the human body is recognized, the intelligent mobile device can perform corresponding processing, such as avoiding the human body or tracking the human body. On the other hand, the curve is judged according with the characteristics of the human leg, certain data processing work is reduced, and the identification efficiency and the working efficiency can be effectively improved.

According to the technical scheme of the embodiment, the human body in the surrounding environment can be accurately identified by combining the curve characteristics of the human body contour for identification and judgment, and the position of the human body is obtained. Meanwhile, the judgment according with the human leg characteristics is only carried out on the curve obtained by scanning, certain data processing work is reduced, and the identification efficiency and the working efficiency can be effectively improved. Moreover, single-line laser is adopted for scanning, so that the scanning efficiency and accuracy can be ensured, and the scanning range is expanded.

In a specific embodiment, the identifying one or more segments of curves formed by the scanning points and conforming to the circular arc characteristics according to the distribution of the scanning points includes: and performing circle fitting according to the distribution condition of the plurality of scanning points to obtain one or more sections of curves formed by the scanning points.

In the above embodiment, the scanning points are connected in sequence to obtain the profile of the object. However, the contour curve obtained by the method is a broken line with discontinuous curvature composed of multiple line segments, and thus does not conform to the objective rule that the contour of a common object is continuous. Therefore, the polygonal line needs to be smoothed so as to better conform to the objective rule of the contour line. For a curve conforming to the characteristics of the circular arc, if the curvature change among a plurality of continuous scanning points is large, the curve is subjected to circle fitting, namely, the curve is processed into a theoretical circular arc.

In a specific embodiment, the identifying one or more segments of curves formed by the scanning points and conforming to the circular arc characteristics according to the distribution of the scanning points includes: when a section of curve conforming to the characteristics of the circular arc is identified, judging whether continuous scanning points exist on the straight lines corresponding to the two end points of the circular arc or not; if yes, estimating the width of the detection object corresponding to the arc according to the continuous scanning points; if the width is larger than the preset value, abandoning the identified curve which accords with the arc characteristics, and not identifying whether the continuous scanning points accord with the arc characteristics.

It can be seen from the above embodiments that the identification of the curve corresponding to the circular arc feature is performed to determine whether the curve corresponds to the human leg feature. Considering that in practice, the width of a normal human leg is generally between 10cm and 20 cm. If the distance between the two end points of the curve exceeds 20cm or is less than 10cm, the width of the curve obviously does not conform to the width of the human leg, so that the curve is filtered, the data volume needing to be judged is reduced, and the efficiency is improved for the next judgment.

On the other hand, the laser has a measurement error during scanning, for example, when a wall is scanned, a wavy scanning spot may be obtained due to the measurement error. This results in a plurality of continuous curves that follow the characteristics of a circular arc. In order to avoid misjudging the curve conforming to the characteristic of the circular arc as a curve conforming to the characteristic of the human leg, special treatment needs to be performed on a plurality of continuous curves conforming to the characteristic of the circular arc. Specifically, two end points of the multi-segment arc are connected to obtain a corresponding straight line. Thus, there must be a continuous scanning point in the middle of the segment of the straight line. And judging whether the width of the first section of arc in the plurality of sections of arcs accords with the width of the human leg, if not, indicating that the corresponding arc is not the curve obtained by scanning the human leg. Similarly, it can be known that all the circular arc curves in the middle of the section of straight line are not the curves obtained by scanning the human legs, so that the identified curves conforming to the circular arc characteristics are abandoned, and whether the continuous scanning points conform to the circular arc characteristics is not identified, so that the data processing amount is reduced, and the identification rate is improved.

In a specific embodiment, the determining whether the identified curves conform to the characteristics of the human leg includes: and judging whether the central angle corresponding to each section of curve is within a first preset angle range, if so, judging that the corresponding curve conforms to the characteristics of the human leg.

When the intelligent mobile device scans by laser, the intelligent mobile device is equivalent to scanning at a fixed position. If the human leg is scanned, only a partial contour of the human leg can be obtained, and the whole closed circular contour cannot be obtained. Therefore, the curve conforming to the characteristics of a human leg should have a certain fan angle. Because the curve can be considered as a circular arc, that is, whether the corresponding curve conforms to the characteristics of the human leg can be effectively identified by judging whether the central angle corresponding to the curve is within the first preset angle range. The first preset angle range is set in combination with the contour curve of the human leg.

In order to improve the determination accuracy, the first preset angle range is set to 60 ° to 120 ° in consideration that the contour curve of the human leg is not theoretically circular. When the central angle corresponding to the curve is between 60 and 120 degrees, the curve is considered to be a curve according with the characteristics of the human leg, and the object corresponding to the curve is considered to be a human body. If the central angle corresponding to the curve is too large or too small, the curve is difficult to match with the actual human leg contour curve, and the curve is judged not to accord with the human leg characteristics.

In a specific embodiment, the determining whether the identified curves conform to the characteristics of the human leg includes: and judging whether each section of curve conforms to the circumferential angle theorem, if so, judging that the corresponding curve conforms to the human leg characteristics.

In addition to the determination based on the central angle of the curve, the determination may be made based on the circumferential angle of the curve. In the actual operation process, the contour curve of a human leg is considered to be a complete circle, and then any section of circular arc obtained from the contour curve should conform to the circumferential angle theorem, that is, the circumferential angles of any point on the circular arc corresponding to the section of circular arc are equal. Therefore, if any point on the curve except for two endpoints of the curve is taken as a vertex, an angle formed by the vertex and the two endpoints is regarded as a circumferential angle of the curve, and if the angles of a plurality of circumferential angles are equal, the curve conforms to the circumferential angle theorem, so that the curve is judged to conform to the characteristics of the human leg.

In a specific example, two end points of a curve are M, N, any three non-overlapping points A, B, C are taken on the curve, A, B, C and M, N are not overlapped, circumferential angles × MAN, × MBN and × MCN of three curves are respectively formed with the two end points M, N, and if the angles of the three circumferential angles are equal, the section of the curve conforms to the circumferential angle theorem.

In a specific embodiment, the determining whether each curve conforms to the circumferential angle theorem includes: for a section of curve, sequentially calculating circumferential angle angles formed by each point on the curve and the first endpoint and the second endpoint from the first endpoint to the second endpoint of the section of curve; if the variation trend of the circumferential angle corresponding to each point is smaller and then larger, the curve is judged to be not in accordance with the circumferential angle theorem.

Considering that the contour curve of a human leg is not actually a theoretical circle, the curve obtained by scanning the human leg does not perfectly conform to the circumferential angle theorem. That is, it is possible that the respective circumferential angles are not equal. In addition, in the laser scanning process, if a wall or other objects with right angles are scanned, a curve is obtained. In order to avoid the occurrence of misjudgment, the judgment accuracy is improved, and the judgment of the circumferential angle theorem is further optimized.

The curve obtained by scanning a right-angled wall or object has a certain rule of circumferential angle change. For example, if the first end point to the second end point along the curve segment, a point on the curve is sequentially taken as a vertex, and a circumferential angle is formed between the vertex and the two end points. The closer to the apex of the end point, the greater its circumferential angle. Therefore, in the circumferential angle formed by sequentially taking points as vertexes, the change rule of the circumferential angle is gradually reduced and then gradually increased.

As in the above specific example, the two end points of the curve are M, N, and starting from point M, a point is sequentially taken on the curve at regular intervals, and a circumferential angle is formed between the two end points. For example, A, B, C, D is taken, A, B, C, D and M, N are not overlapped, and circumferential angles ═ MAN,. sub.MBN,. sub.MCN and. sub.MDN of four curves are formed with two end points M, N respectively. The transformation rules of the four circumferential angles are firstly reduced and increased, namely < MAN > < MBN and < MCN < MDN. When the change rule of firstly becoming smaller and then becoming larger is judged to be met among all the circumferential angles, the curve is considered to be the curve obtained by scanning the right-angle part. And the contour curve of the human leg does not have a right-angle characteristic, so that the curve is judged to be not in accordance with the circumferential angle theorem, namely, the human leg characteristic is not in accordance.

In a specific embodiment, the determining whether each curve conforms to the circumferential angle theorem includes: for a section of curve, sequentially calculating circumferential angle angles formed by each point on the curve and the first endpoint and the second endpoint from the first endpoint to the second endpoint of the section of curve; and calculating the mean square error of each circumferential angle, and if the mean square error is greater than a preset value, judging that the curve does not conform to the circumferential angle theorem.

Considering that the profile curve of a human leg is not actually a theoretical circle, the curve obtained by scanning the human leg does not perfectly conform to the circumferential angle theorem, but the respective circumferential angles fluctuate within a certain angular range. And obtaining the dispersion degree of the circumferential angle by judging the mean square error of each circumferential angle. If the discrete degree is within the preset range, the curve is considered to conform to the circumferential angle theorem.

Taking the above embodiment as an example, the two end points of the curve are M, N, and starting from point M, a point is sequentially taken on the curve at regular intervals, and a circumferential angle is formed between the two end points. For example, A, B, C, D is taken, A, B, C, D and M, N are not overlapped, and circumferential angles ═ MAN,. sub.MBN,. sub.MCN and. sub.MDN of four curves are formed with two end points M, N respectively. And calculating the mean square deviations of the four circumferential angles, and if the mean square deviations are smaller than a preset value, indicating that the dispersion degrees of the four circumferential angles are smaller, judging that the curve conforms to the circumferential angle theorem. If the mean square error is larger than the preset value, which shows that the dispersion degree of the four circumferential angles is larger, the curve is judged to be not in accordance with the circumferential angle theorem. For example, if the mean square error is 0, it indicates that the angles of the four circumferential angles are equal to each other, and the preset value is 0.5. If the mean square error is 2 and is larger than 0.5, the dispersion degree of the four circumference angles is larger, the curvature change of the curve is larger, and the curve does not accord with the contour curve characteristics of human legs.

In a specific embodiment, the determining the detected position of the human body according to the corresponding curve includes: and if the distance between the two curves is smaller than a preset value, determining the same human body according to the two curves.

One person has two corresponding legs, and two sections of curves which accord with the characteristics of the legs of the person can be obtained with high probability in the laser scanning process. Considering that in reality, the distance between two legs generally does not exceed a certain value, the distance between two curves is judged to determine whether the two curves belong to the same person. For example, an adult who normally walks, the distance between the legs is 60 cm. And setting the distance preset value of the curve to be 75cm, judging that the two curves belong to two legs of the same person when the distance between the two curves is less than 75cm, and determining the position of the human body according to the positions of the two curves. For example, one curve is 100cm away from the smart mobile device, the other curve is 80cm away from the smart mobile device, the middle value of the two curves is taken, and the position of the human body is determined to be 90cm away from the smart mobile device.

There is of course also a case where only one curve may be obtained during the scanning process, which corresponds to the characteristics of a human leg. In this case, the segment of the curve is also considered to be a human leg contour curve, and the human leg position is determined from the position of the curve. In the actual scanning process, there may be a situation that two legs coincide and two curves conforming to the characteristic curves of the legs cannot be obtained, for example, when the intelligent mobile device is located on the side of the human body and scanning is performed from the side, two legs of the human body coincide and two curves cannot be obtained.

In a specific embodiment, the scanning the surrounding environment of the smart mobile device by the single-line laser includes: 360 DEG surrounding scanning is carried out at a preset frequency through a laser radar.

The single line laser is a laser radar, and in order to reduce a certain data processing amount, in the actual scanning process, the laser radar does not scan continuously in real time but scans at a preset frequency. For example, one scanning is performed at intervals of 1s, 5s and 8s, and it is ensured that a certain time is left for processing the scanning result after each scanning is completed so as to ensure the accuracy of the result. Set up lidar on intelligent mobile device's rotary platform, rotate or rotate lidar alone as intelligent mobile device, lidar can realize 360 encircleing the scanning, obtains the profile information of all objects of all ring borders.

In one embodiment of the present invention, in the method shown in fig. 1, the planning of the path from the current location of the smart mobile device to the target point in step S110 includes: and searching a track line from the current position of the intelligent mobile device to the target point based on the A-x algorithm.

The algorithm A is the most effective direct search method for solving the shortest path in the static road network, and is also an effective algorithm for solving the problem of searching a plurality of paths. And determining the current position and the target point position of the intelligent mobile equipment, and quickly searching to obtain a track line between the current position and the target point position by using an A-x algorithm, wherein the closer the distance estimation value and the actual distance value are, the faster the final searching speed is. Thus, the tracking efficiency of the intelligent mobile device can be further improved.

In an embodiment of the present invention, in the method shown in fig. 1, the tracking the tracked object in step S120 includes: detecting at a preset frequency; and taking the detected object which accords with the preset characteristics as a tracking object, and recording the position of the detected tracking object.

The tracking object has autonomous mobility, and in the tracking process, in order to ensure that the tracking object is not lost, the position of the tracking object needs to be continuously detected and recorded, so that accurate tracking can be realized. In the process, determination of the tracked object is also involved, and the specific method for determining the tracked object can adopt the determination method provided by the above embodiment. Meanwhile, the higher the detection frequency is, the higher the tracking accuracy is, and the more data need to be processed; the low detection frequency may cause the loss of the tracking object. Therefore, the detection frequency is preset according to specific situations, such as one detection at an interval of 3s, or 500ms, 1s, etc.

Taking the sweeping robot to track the human body as an example, the sweeping robot uses a single-line laser to perform detection every 1 s. When the single-line laser detects the characteristics corresponding to the human legs, the object corresponding to the characteristics is determined to track the human legs, and the positions of the characteristics are recorded so as to realize accurate tracking.

In an embodiment of the present invention, in the method, the adjusting the target point according to the tracking result in step S120 includes: determining a predicted position according to the positions of the tracking objects recorded for the last times; if the object which accords with the preset characteristics is continuously detected in a second preset range of the predicted position, taking the object which accords with the preset characteristics detected this time as a tracking object; and taking the position of the detected tracking object as an adjusted target point.

According to a plurality of positions of the tracking object, the moving track of the tracking object can be fitted, and the next moving position of the tracking object can be determined according to the moving track, namely the predicted position is determined. In general, since it is considered that the tracking target moves to the predicted position, when the tracking target is detected, the detection range is narrowed by preferentially detecting the range near the predicted position, thereby improving the detection efficiency. For example, a range within 100cm around the predicted position is preferentially detected, and if an object that meets the preset characteristics is detected, the object is determined to be the tracking object. If no object meeting the preset characteristics is detected, other ranges are detected. The second predetermined range may be set according to practical settings, such as 50cm, 100cm, etc.

In an embodiment of the present invention, the determining the predicted position according to the last recorded tracking object positions includes: and performing Kalman filtering processing on the positions of the tracking objects recorded for a plurality of times recently.

By using kalman filtering, noise points in the location points can be removed to make the determined predicted location more consistent with the movement of the tracked object. Meanwhile, redundant position points are removed, so that the track of the moving image is easier to fit and track. For example, in 10 continuously recorded positions, data of a position point deviating from other position points exist, the data are removed by Kalman filtering, the influence of the data on the determination of the predicted position is avoided, and the accuracy is improved.

In a specific example, the tracking object is detected every 500ms, 120 position points are obtained within 1min, and when the trajectory of the tracking object is fitted, too much data needs to be processed, which affects the efficiency of determining the predicted position. And removing redundant position points through Kalman filtering, and reserving the position points which accord with the movement rule of the tracked object, such as reserving 20 position points, so that the movement trajectory line can be quickly calculated, and the predicted position is determined.

In an embodiment of the present invention, the method, wherein the taking the object detected to meet the preset characteristic as the tracking object includes: and if a plurality of objects which accord with the preset characteristics are detected, taking the object which is closest to the predicted position as a tracking object.

During the tracking process, it may occur that a plurality of objects conforming to the preset characteristics are detected. In this case, it is necessary to determine an object as a tracking object from among a plurality of objects that meet a preset characteristic, so that the smart mobile device can perform accurate tracking.

In the above example, the predicted position is determined based on the moving trajectory line of the tracking target, and in the case where a plurality of objects conforming to the preset feature are detected, the predicted position is considered as the destination of the tracking target. Therefore, the distance from each object conforming to the preset characteristics to the predicted position is calculated according to the position of the object, and the object closest to the predicted position is taken as the tracking object.

For example, the predicted position is point a, three objects B, C and D meeting the preset characteristics exist in the detection process, and the object B is determined to be closest to point a by distance calculation, thereby determining that object B is the tracking object.

In one embodiment of the present invention, as in the method shown in fig. 1, the method further comprises: if the current position of the intelligent mobile device and the range of the adjusted target point are within the first preset range, the path is not re-planned according to the adjusted target point.

In order to improve the tracking efficiency and the working efficiency of the intelligent mobile device, the intelligent mobile device plans a path and travels only when a tracked object is far away. The distance between the adjusted target point and the current position of the intelligent mobile device is within a first preset range, which indicates that the tracked object is not far away, but may be circling nearby, and at this time, if the path is re-planned, the intelligent mobile device can also be circling in place. Therefore, not only the accurate tracking is not carried out, but also the electric quantity is consumed, and the working efficiency is influenced. In this case, therefore, there is no need to re-plan the path. The first preset range may be set according to practical implementation, for example, 50cm, 70cm, 100cm, or the like.

In a specific example, the distance between the target point and the smart mobile device is 50cm before the target point is adjusted, and the distance between the adjusted target point and the smart mobile device is 20cm after the target point is adjusted, which indicates that the tracked object approaches the smart mobile device, and if the smart mobile device replans a path to move forward, the tracked object may collide with the tracked object. Thus, in this case, the path does not need to be re-planned according to the adjusted target point, but the detection of the tracked object is maintained to determine the next target point. Meanwhile, the intelligent mobile equipment is fixed in place and rotates along with the moving direction of the tracked object.

In an embodiment of the present invention, in the method shown in fig. 1, the re-planning the path according to the adjusted target point in step S130 includes: and if the position change speed of the tracked object is determined to be greater than the preset speed according to the tracking result, determining a starting point according to a first preset range with the current position of the intelligent mobile equipment as the circle center and the currently planned path, and planning the path from the starting point to the adjusted target point.

The speed of change of the position, that is, the moving speed of the tracking object can be determined based on the current position of the tracking object and the recorded previous position. Since the detection interval is fixed, the moving speed of the tracking object can be acquired by the distance between the positions.

In the above example, the smart device needs to move to the current target point and then move from the current target point to the next target point. When the moving speed of the tracked object is greater than the preset speed, in order to ensure that the intelligent mobile device can keep up with the tracked object, the intelligent mobile device needs to plan a more reasonable path. That is, the smart mobile device does not need to move to the current target point, but directly plans a new path to move to the next target point. The new path is a path from the starting point to the adjusted target point, namely the next target point, which is determined according to the first preset range taking the current position of the intelligent mobile device as the circle center and the currently planned path. The starting point is an intersection point of the boundary of the first preset range and the currently planned path, and the intelligent mobile device moves to the point and moves from the point to the adjusted target point. Therefore, the intelligent mobile equipment does not need to move to the current target point, the moving distance is shortened, and the moving time is fully saved so as to keep up with the tracking object. Meanwhile, the intelligent mobile equipment can be ensured to be continuous in the moving process, and the phenomenon that the intelligent mobile equipment stops or moves discontinuously is avoided.

In a specific embodiment, the smart mobile device needs to move from point a to point B and then from point B to point C. If the speed of the tracked object is increased, the intelligent robot may lose the tracked object according to the planned path. Therefore, the intersection point of the circle with the point A range of 50cm and the path from A to B is planned again to be the starting point, and the path from the starting point to C is planned. Thus, the smart mobile device moves from a to the starting point and then from the starting point to C. Since the starting point is closer to a, the adjusted path is equivalent to moving from a to C, thereby shortening a certain moving distance.

In an embodiment of the present invention, in the method shown in fig. 1, the smart mobile device is a sweeping robot, and the tracked object is a human body.

The sweeping robot tracks the human body. Therefore, the sweeping robot can sweep under the belt of a person, so that collision with a barrier is effectively avoided, the damage risk of the sweeping robot is reduced, and the service life of the sweeping robot is prolonged. For example, in a general living room, a lot of articles are placed, and under the guidance of a person, the sweeping robot can sweep the moving area of the person, so that obstacles are effectively avoided. Meanwhile, the sweeping robot does not need to get rid of difficulties and search for a sweeping route, and the sweeping efficiency can be greatly improved.

Fig. 2 is a schematic structural diagram of a global path planning apparatus of an intelligent mobile device according to an embodiment of the present invention. As shown in fig. 2, the apparatus 200 includes:

a determination unit 210 adapted to determine a tracked object; and determining a target point according to the current position of the tracking object, and planning a path from the current position of the intelligent mobile equipment to the target point.

The adjusting unit 220 is adapted to track the tracked object and adjust the target point according to the tracking result.

And a path planning unit 230 adapted to re-plan the path according to the adjusted target point.

In an embodiment of the invention, as shown in the apparatus 200 of fig. 2, the determining unit 210 is adapted to perform detection by a depth camera and/or a lidar and determine a detected object that meets a preset characteristic as a tracking object.

For example, the sweeping robot tracks the human body, detects the human body by using a laser radar, can detect partial human legs, and is characterized by being semicircular and having a certain distance between the two legs. That is, when a single line laser detects a leg of a person, two semicircular arc features having a distance within a certain range can be obtained, or when one leg is detected, one semicircular arc feature is obtained, thereby determining that the semicircular arc feature corresponds to a human body and using the human body as a tracking object.

In an embodiment of the present invention, in the apparatus 200 shown in fig. 2, the determining unit 210 is adapted to search for a trajectory from the current location of the smart mobile device to the target point based on the a-x algorithm.

In an embodiment of the present invention, as shown in the apparatus 200 of fig. 2, the adjusting unit 220 is adapted to perform the detection at a predetermined frequency; and taking the detected object which accords with the preset characteristics as a tracking object, and recording the position of the detected tracking object.

In an embodiment of the present invention, in the apparatus 200, the adjusting unit 220 is further adapted to determine a predicted position according to the last recorded positions of the tracking object; if the object which accords with the preset characteristics is continuously detected in a second preset range of the predicted position, taking the object which accords with the preset characteristics detected this time as a tracking object; and taking the position of the detected tracking object as an adjusted target point.

In an embodiment of the present invention, in the apparatus 200, the adjusting unit 220 is further adapted to perform kalman filtering on the positions of the tracking objects recorded several times last.

In an embodiment of the invention, in the apparatus 200, the adjusting unit 220 is further adapted to, if a plurality of objects meeting the preset characteristics are detected, take an object closest to the predicted position as a tracking object.

In one embodiment of the present invention, as in the apparatus 200 shown in fig. 2, the apparatus further comprises: and the judging unit is suitable for not re-planning the path according to the adjusted target point if the current position of the intelligent mobile equipment and the range of the adjusted target point are within a first preset range.

In an embodiment of the present invention, as shown in the apparatus 200 shown in fig. 2, the path planning unit 230 is adapted to determine a starting point according to a first preset range in which the current position of the smart mobile device is a circle center and a currently planned path if it is determined that the position change speed of the tracked object is greater than a preset speed according to the tracking result, and plan a path from the starting point to the adjusted target point.

In an embodiment of the present invention, as shown in the apparatus 200 shown in fig. 2, the smart mobile device is a sweeping robot, and the tracked object is a human body.

In summary, according to the technical solution of the present invention, the target point is determined according to the current position of the tracked object by determining the tracked object, and a path from the current position of the intelligent mobile device to the target point is planned. And tracking the tracked object, and adjusting the target point according to the tracking result. And re-planning the path according to the adjusted target point. According to the technical scheme, before tracking is started, the advancing direction of the intelligent mobile equipment is determined, so that the intelligent mobile equipment has advancing basis, and loss caused by too high moving speed of a tracked object is avoided. In the tracking process, prejudgment is carried out in advance, the position of the target point is adjusted in time, the advancing direction of the intelligent mobile equipment is adjusted, invalid advancing is avoided, and tracking efficiency is improved.

It should be noted that:

the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of a global path planning apparatus, an electronic device, a computer-readable storage medium, and a smart mobile device according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

For example, fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the invention. The electronic device comprises a processor 310 and a memory 320 arranged to store computer executable instructions (computer readable program code). The memory 320 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 320 has a storage space 330 storing computer readable program code 331 for performing any of the method steps described above. For example, the storage space 330 for storing the computer readable program code may comprise respective computer readable program codes 331 for respectively implementing various steps in the above method. The computer readable program code 331 may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a computer readable storage medium such as described in fig. 4. Fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention. The computer readable storage medium 400 has stored thereon a computer readable program code 331 for performing the steps of the method according to the invention, readable by a processor 310 of the electronic device 300, which computer readable program code 331, when executed by the electronic device 300, causes the electronic device 300 to perform the steps of the method described above, in particular the computer readable program code 331 stored on the computer readable storage medium may perform the method shown in any of the embodiments described above. The computer readable program code 331 may be compressed in a suitable form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

The invention provides a1 and a global path planning method of intelligent mobile equipment, which comprises the following steps:

determining a tracking object;

and re-planning the path according to the adjusted target point.

A2, the method of A1, wherein the determining a tracked object comprises: and detecting through a depth camera and/or a laser radar, and determining the detected object which accords with the preset characteristics as a tracking object.

A3, the method as in a1, wherein the planning a path from a current location of a smart mobile device to the target point comprises: and searching a track line from the current position of the intelligent mobile device to the target point based on the A-x algorithm.

A4, the method as in A1, wherein the tracking the tracked object comprises:

detecting at a preset frequency; and taking the detected object which accords with the preset characteristics as a tracking object, and recording the position of the detected tracking object.

A5, the method as in A4, wherein the adjusting the target point according to the tracking result comprises:

A6, the method as in A5, wherein the determining a predicted position from the last several recorded positions of tracked objects comprises: and performing Kalman filtering processing on the positions of the tracking objects recorded for a plurality of times recently.

A7, the method as recited in a5, wherein the step of taking the object which is detected to meet the preset characteristics as the tracking object includes: and if a plurality of objects which accord with the preset characteristics are detected, taking the object which is closest to the predicted position as a tracking object.

A8, the method of a1, wherein the method further comprises: if the current position of the intelligent mobile device and the range of the adjusted target point are within a first preset range, the path is not re-planned according to the adjusted target point.

A9, the method as claimed in a1, wherein the re-planning the path according to the adjusted target points comprises: and if the position change speed of the tracked object is determined to be greater than the preset speed according to the tracking result, determining a starting point according to a first preset range with the current position of the intelligent mobile equipment as the circle center and the currently planned path, and planning the path from the starting point to the adjusted target point.

A10, the method according to A1, wherein the intelligent mobile device is a sweeping robot, and the tracked object is a human body.

The invention also provides B11, a global path planning device of the intelligent mobile device, comprising:

B12, the device according to B11, wherein the determining unit is adapted to detect by a depth camera and/or a lidar and determine the detected object meeting the preset characteristics as the tracking object.

B13, the apparatus according to B11, wherein the determining unit is adapted to search for a trajectory from the current location of the smart mobile device to the target point based on B-algorithm.

B14, the device as in B11, wherein the adjusting unit is suitable for detecting at a preset frequency; and taking the detected object which accords with the preset characteristics as a tracking object, and recording the position of the detected tracking object.

B15, the device as claimed in B14, wherein the adjusting unit is further adapted to determine the predicted position according to the last recorded positions of the tracked object;

B16, the device as in B15, wherein the adjusting unit is further adapted to perform kalman filtering processing on the last several recorded positions of the tracked object.

B17, the device according to B15, wherein the adjusting unit is further adapted to, if a plurality of objects matching the preset characteristics are detected, take the object closest to the predicted position as the tracking object.

B18, the apparatus of B11, wherein the apparatus further comprises:

B19, the apparatus according to B11, wherein the path planning unit is adapted to determine a starting point according to a first preset range in which the current position of the smart mobile device is the center of a circle and the currently planned path if it is determined that the speed of change of the position of the tracked object is greater than a preset speed according to the tracking result, and plan the path from the starting point to the adjusted target point.

B20, the device according to B11, wherein the intelligent mobile device is a sweeping robot, and the tracked object is a human body.

The invention also provides C21, an electronic device, wherein the electronic device comprises: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of any one of a1-a 10.

The invention also provides D22, a computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method of any of a1-a 10.

Claims

1. A global path planning method of an intelligent mobile device comprises the following steps:

determining a tracking object;

and re-planning the path according to the adjusted target point.

2. The method of claim 1, wherein the determining a tracked object comprises:

3. The method of claim 1, wherein planning the path from the current location of the smart mobile device to the target point comprises:

4. The method of claim 1, wherein the tracking the tracked object comprises:

detecting at a preset frequency;

5. The method of claim 4, wherein the adjusting the target point according to the tracking result comprises:

6. The method of claim 5, wherein the determining a predicted location from the last recorded positions of the tracked object comprises:

7. The method according to claim 5, wherein the step of using the detected object meeting the preset characteristic as the tracking object comprises the following steps:

8. A global path planning device of an intelligent mobile device comprises:

9. An electronic device, wherein the electronic device comprises: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method of any one of claims 1-7.

10. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method of any of claims 1-7.